© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 86052
    Prev
    Next
    INDEX
    Explanations

    file formats or numerical values typically associated with image and data processing

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    orer
    -0.07
    vers
    -0.06
     distinct
    -0.06
    oon
    -0.06
    eler
    -0.06
    ion
    -0.06
    .cg
    -0.06
     functions
    -0.06
    rah
    -0.06
     ing
    -0.06
    POSITIVE LOGITS
    GMEM
    0.08
    оÑĢож
    0.08
    HEMA
    0.07
     addCriterion
    0.06
    LTRB
    0.06
    ooks
    0.06
    udur
    0.06
    htar
    0.06
    GuidId
    0.06
     RequestOptions
    0.06
    Activations Density 0.006%

    No Known Activations